Research Intern, Inference (Winter 2027)

Together AI is seeking a research intern to join their Inference Research team, which focuses on developing efficient and scalable serving systems for large foundation models. The team works at the intersection of model architectures, systems engineering, and hardware optimization to reduce costs and latency in AI systems. The intern will contribute to projects aimed at improving model deployment speed, scale, and robustness, working on cutting-edge inference techniques.

Daily tasks include designing experiments, analyzing results, and documenting findings for scientific publications and blogs. The role requires a background in computer science or electrical engineering, with knowledge of machine learning, deep learning frameworks, and transformer architectures. The internship offers remote or onsite work, with a 12-14 week program, competitive pay, and housing stipends, providing an excellent environment for emerging researchers.

This position is ideal for students in their final year of study or recent graduates with research experience in foundation models or ML systems. Preferred skills include CUDA programming, hardware acceleration, and contributions to open-source projects. The internship is a contract role, with compensation based on experience, and is open to applicants in the San Francisco area or remote.